|Authors: ||M. Fiers, T. Van Vaerenbergh, F. Wyffels, D. Verstraeten, B. Schrauwen, J. Dambre, P. Bienstman|
|Title: ||Nanophotonic reservoir computing with photonic crystal cavities to generate periodic patterns|
|Format: ||International Journal|
|Publication date: ||2/2014|
|Journal/Conference/Book: ||IEEE Transactions on Neural Networks and Learning Systems
|Editor/Publisher: ||Prof. Derong Liu, |
|Volume(Issue): ||25(2) p.344 - 355|
|Citations: ||30 (Dimensions.ai - last update: 17/10/2021)|
17 (OpenCitations - last update: 19/4/2021)
Look up on Google Scholar
Reservoir computing (RC) is a technique in machine learning inspired by neural systems. RC has been used successfully to solve complex problems such as signal classification and signal generation. These systems are mainly implemented in software, and thereby they are limited in speed and power efficiency. Several optical and opto-electronic implementations have been demonstrated, in which the system has signals with an amplitude and phase. It is proven that these enrich the dynamics of the system which is beneficial for the performance.
In this paper we introduce a novel optical architecture based on nanophotonic crystal cavities. This allows us to integrate many neurons on one chip, which, compared to other photonic solutions, closest resembles a classical neural network. Furthermore the components are passive, which simplifies the design and reduces the power consumption.
To assess the performance of this network, we train a photonic network to generate periodic patterns, using an alternative online learning rule called FORCE. For this we first train a classical hyperbolic tangent reservoir, but then we vary some of the properties to incorporate typical aspects of a photonics reservoir, such as the use of continuous-time signals versus discrete-time signals and the use of complex-valued signals versus real-valued signals.
Then the nanophotonic reservoir is simulated and we explore the role of relevant parameters such as the topology, the phases between the resonators, the number of nodes that are biased and the delay between the resonators. It is important that these parameters are chosen such that no strong self-oscillations occur.
Finally, our results show that for a signal generation task a complex-valued, continuous-time nanophotonic reservoir outperforms a classical (i.e., discrete-time, real-valued) leaky hyperbolic tangent reservoir (NRMSE = 0.030 vs. NRMSE= 0.127).
Related Research Topics